@inproceedings{nordhoff-2020-attic,
title = "From the attic to the cloud: mobilization of endangered language resources with linked data",
author = "Nordhoff, Sebastian",
editor = "Broeder, Daan and
Eskevich, Maria and
Monachini, Monica",
booktitle = "Proceedings of the Workshop about Language Resources for the SSH Cloud",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lr4sshoc-1.3",
pages = "10--18",
abstract = "This paper describes a collection of 20k ELAN annotation files harvested from five different endangered language archives. The ELAN files form a very heterogeneous set, but the hierarchical configuration of their tiers allow, in conjunction with the tier content, to identify transcriptions, translations, and glosses. These transcriptions, translations, and glosses are queryable across archives. Small analyses of graphemes (transcription tier), grammatical and lexical glosses (gloss tier), and semantic concepts (translation tier) show the viability of the approach. The use of identifiers from OLAC, Wikidata and Glottolog allows for a better integration of the data from these archives into the Linguistic Linked Open Data Cloud.",
language = "English",
ISBN = "979-10-95546-43-6",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nordhoff-2020-attic">
<titleInfo>
<title>From the attic to the cloud: mobilization of endangered language resources with linked data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Nordhoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop about Language Resources for the SSH Cloud</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daan</namePart>
<namePart type="family">Broeder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Eskevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="family">Monachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-43-6</identifier>
</relatedItem>
<abstract>This paper describes a collection of 20k ELAN annotation files harvested from five different endangered language archives. The ELAN files form a very heterogeneous set, but the hierarchical configuration of their tiers allow, in conjunction with the tier content, to identify transcriptions, translations, and glosses. These transcriptions, translations, and glosses are queryable across archives. Small analyses of graphemes (transcription tier), grammatical and lexical glosses (gloss tier), and semantic concepts (translation tier) show the viability of the approach. The use of identifiers from OLAC, Wikidata and Glottolog allows for a better integration of the data from these archives into the Linguistic Linked Open Data Cloud.</abstract>
<identifier type="citekey">nordhoff-2020-attic</identifier>
<location>
<url>https://aclanthology.org/2020.lr4sshoc-1.3</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>10</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From the attic to the cloud: mobilization of endangered language resources with linked data
%A Nordhoff, Sebastian
%Y Broeder, Daan
%Y Eskevich, Maria
%Y Monachini, Monica
%S Proceedings of the Workshop about Language Resources for the SSH Cloud
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-43-6
%G English
%F nordhoff-2020-attic
%X This paper describes a collection of 20k ELAN annotation files harvested from five different endangered language archives. The ELAN files form a very heterogeneous set, but the hierarchical configuration of their tiers allow, in conjunction with the tier content, to identify transcriptions, translations, and glosses. These transcriptions, translations, and glosses are queryable across archives. Small analyses of graphemes (transcription tier), grammatical and lexical glosses (gloss tier), and semantic concepts (translation tier) show the viability of the approach. The use of identifiers from OLAC, Wikidata and Glottolog allows for a better integration of the data from these archives into the Linguistic Linked Open Data Cloud.
%U https://aclanthology.org/2020.lr4sshoc-1.3
%P 10-18
Markdown (Informal)
[From the attic to the cloud: mobilization of endangered language resources with linked data](https://aclanthology.org/2020.lr4sshoc-1.3) (Nordhoff, LR4SSHOC 2020)
ACL